Data Extractaction and Exploration

library(opendatascot)
library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ─────────────────────────────────────────────────────────────────────────── tidyverse 1.3.0 ──
✓ ggplot2 3.3.3     ✓ purrr   0.3.4
✓ tibble  3.0.6     ✓ dplyr   1.0.2
✓ tidyr   1.1.2     ✓ stringr 1.4.0
✓ readr   1.4.0     ✓ forcats 0.5.0
── Conflicts ────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

ods_all_datasets() %>% 
  janitor::clean_names() %>% 
  filter(name == "Life Expectancy") %>% 
  select(uri)

ods_structure("healthy-life-expectancy")

$schemes
[1] "http://purl.org/linked-data/sdmx/2009/dimension#refArea"          
[2] "http://purl.org/linked-data/sdmx/2009/dimension#refPeriod"        
[3] "http://purl.org/linked-data/cube#measureType"                     
[4] "http://statistics.gov.scot/def/dimension/sex"                     
[5] "http://statistics.gov.scot/def/dimension/age"                     
[6] "http://statistics.gov.scot/def/dimension/simdQuintiles"           
[7] "http://statistics.gov.scot/def/dimension/urbanRuralClassification"

$categories
$categories$refArea
 [1] "S12000005" "S12000006" "S12000008" "S12000010" "S12000011" "S12000013" "S12000014" "S12000047" "S12000017"
[10] "S12000018" "S12000019" "S12000020" "S12000021" "S12000023" "S12000048" "S12000026" "S12000027" "S12000028"
[19] "S12000029" "S12000030" "S12000033" "S12000034" "S12000035" "S12000036" "S12000038" "S12000039" "S12000040"
[28] "S12000041" "S12000042" "S12000050" "S12000045" "S12000049" "S92000003" "S08000015" "S08000016" "S08000017"
[37] "S08000019" "S08000020" "S08000031" "S08000022" "S08000032" "S08000024" "S08000025" "S08000026" "S08000028"
[46] "S08000029" "S08000030"

$categories$refPeriod
[1] "P3Y" "P3Y" "P3Y"

$categories$measureType
[1] "count"                     "95-lower-confidence-limit" "95-upper-confidence-limit"

$categories$sex
[1] "male"   "female"

$categories$age
 [1] "0-years"     "1-4-years"   "5-9-years"   "10-14-years" "15-19-years" "20-24-years" "25-29-years" "30-34-years"
 [9] "35-39-years" "40-44-years" "45-49-years" "50-54-years" "55-59-years" "60-64-years" "65-69-years" "70-74-years"
[17] "75-79-years" "80-84-years" "85-89-years" "90-years"   

$categories$simdQuintiles
[1] "all"              "1-most-deprived"  "2"                "3"                "4"               
[6] "5-least-deprived"

$categories$urbanRuralClassification
[1] "all"                    "large-urban-areas"      "other-urban-areas"      "accessible-small-towns"
[5] "remote-small-towns"     "accessible-rural"       "remote-rural"          

hle_structure <- ods_structure("healthy-life-expectancy")

hle_structure$categories$refPeriod <- c("2015-2017", "2016-2018", "2017-2019")

le_structure <- ods_structure("Life-Expectancy")

le_structure$categories$refPeriod

 [1] "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y"
[19] "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y"

ods_dataset("homelessness-applications",
                          applicationType = "all-applications")

ods_structure("healthy-life-expectancy")$categories$refPeriod

[1] "P3Y" "P3Y" "P3Y"

ods_structure("Life-Expectancy")$categories$refPeriod

 [1] "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y"
[19] "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y" "P3Y"

ods_structure("homelessness-applications")$categories$refPeriod

 [1] "2007-2008" "2008-2009" "2009-2010" "2010-2011" "2011-2012" "2012-2013" "2013-2014" "2014-2015" "2015-2016"
[10] "2016-2017" "2017-2018" "2018-2019" "2019-2020"

ods_dataset("healthy-life-expectancy",
            refPeriod = "P3Y",
            age = "0-years",
            simdQuintiles = "all",
            urbanRuralClassification = "all",
            measureType = "count") %>% 
  filter(age == "0-years") %>% 
  select(-c(simdQuintiles, measureType, urbanRuralClassification, age)) %>% 
  filter(refArea == "S92000003")

library(rgdal)

Loading required package: sp
rgdal: version: 1.5-18, (SVN revision 1082)
Geospatial Data Abstraction Library extensions to R successfully loaded
Loaded GDAL runtime: GDAL 3.1.4, released 2020/10/20
Path to GDAL shared files: /Library/Frameworks/R.framework/Versions/4.0/Resources/library/rgdal/gdal
GDAL binary built with GEOS: TRUE 
Loaded PROJ runtime: Rel. 6.3.1, February 10th, 2020, [PJ_VERSION: 631]
Path to PROJ shared files: /Library/Frameworks/R.framework/Versions/4.0/Resources/library/rgdal/proj
Linking to sp version:1.4-4
To mute warnings of possible GDAL/OSR exportToProj4() degradation,
use options("rgdal_show_exportToProj4_warnings"="none") before loading rgdal.

hb_shapes <- readOGR(
  dsn ="data/simplified_shapefiles/health_boards/NHS_HealthBoards_2019/",
  layer = "NHS_HealthBoards_2019",
  GDAL1_integer64_policy = TRUE)

Discarded datum OSGB_1936 in CRS definition: +proj=tmerc +lat_0=49 +lon_0=-2 +k=0.9996012717 +x_0=400000 +y_0=-100000 +ellps=airy +units=m +no_defs

OGR data source with driver: ESRI Shapefile 
Source: "/Users/user/scot_stats_dashboard/data/simplified_shapefiles/health_boards/NHS_HealthBoards_2019", layer: "NHS_HealthBoards_2019"
with 14 features
It has 4 fields

library(rgeos)

rgeos version: 0.5-5, (SVN revision 640)
 GEOS runtime version: 3.8.1-CAPI-1.13.3 
 Linking to sp version: 1.4-2 
 Polygon checking: TRUE 

hb_simple <- gSimplify(hb_shapes, tol = 0.025, topologyPreserve = TRUE)

56.3950° N, 3.4308° W

uk_shape <- readOGR(
   dsn ="../Downloads/scot_stats_dashboard/bdline_essh_gb/Data/GB/",
   layer = "county_region",
   GDAL1_integer64_policy = TRUE)

Discarded datum OSGB_1936 in CRS definition: +proj=tmerc +lat_0=49 +lon_0=-2 +k=0.9996012717 +x_0=400000 +y_0=-100000 +ellps=airy +units=m +no_defs

OGR data source with driver: ESRI Shapefile 
Source: "/Users/user/Downloads/scot_stats_dashboard/bdline_essh_gb/Data/GB", layer: "county_region"
with 26 features
It has 15 fields
Integer64 fields read as doubles:  NUMBER NUMBER0 POLYGON_ID UNIT_ID 

 
 uk_simple <- gSimplify(uk_shape, tol = 0.025, topologyPreserve = TRUE)

plot(uk_simple)

library(maps)

Attaching package: ‘maps’

The following object is masked from ‘package:purrr’:

    map

UK <- map_data("world") %>% filter(region == "UK")

UK

library(rnaturalearth)
library(rnaturalearthdata)
library(rgeos)

country_uk <- world %>%
  filter(name == "United Kingdom")

poly_uk <- as(country_uk, 'Spatial')

Discarded datum Unknown based on WGS84 ellipsoid in CRS definition

poly_uk@polygons

library(broom)

hle_map_data <- spdf_fortified %>% 
  left_join(hb_lookup, by = c("id" = "id")) %>% 
  left_join(hle_data, by = c("hb_name" = "reference_area"))

library(plotly)

Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

filtered_hle_data <- hle_map_data %>% 
  filter(ref_period == "2015-2017") %>%
  filter(sex =="male")
  

plotly::ggplotly( 
  ggplot() + 
    geom_polygon(data = hle_map_data,
                 aes(x = long, y = lat, group = group,
                     fill = healthy_life_expectancy,
                     text = paste0(hb_name, ": ", healthy_life_expectancy,"years")),
                 colour = "white", size = 0.25) +
    xlim(-7.7,-0.3) +
    scale_fill_viridis_c() +
    coord_map() +
    theme_void(),
  tooltip = "text"
) %>% config(displayModeBar = FALSE) %>%
  layout(xaxis = list(fixedrange = TRUE)) %>%
  layout(yaxis = list(fixedrange = TRUE))

Ignoring unknown aesthetics: text

my_map

hb_shapes@data <- hb_shapes@data %>% 
  janitor::clean_names() %>% 
  left_join(hle_2015_m, by = c("hb_name" = "reference_area"))

labels <- sprintf("<strong>%s</strong><br/>%g years",
                  hb_shapes$hb_name, hb_shapes$healthy_life_expectancy) %>%
  lapply(htmltools::HTML)

# add Health Board polygons, colour based on LE, highlight on hover

my_map %>% 
    addPolygons(data = hb_shapes, color = "white",
                fillColor = ~colorQuantile(
                  "YlOrRd", (-hb_shapes$healthy_life_expectancy))
                (-hb_shapes$healthy_life_expectancy),
                weight = 1, fillOpacity = 0.9, label = labels,
                highlightOptions = highlightOptions(
                  color = "black", weight = 2,
                  opacity = 0.9, bringToFront = TRUE))